Explainable and Trustworthy Automated Software Development with Semantic-based Generative AI

About the Project

Automatic design and development of software applications has been the dream of software communities for decades. Although it can bring significant benefits including increasing productivity, reducing human errors and speeding up development, automatic software development has never been realised properly due to the limitation of software engineering technologies, lack of AI support or the limitation of the existing AI technologies, and leaves the automatic generation of software infeasible, inaccurate, unscalable, untrustworthy and with no explainability of its underlining logic.

There are different software engineering technologies to support automatic software development. Automatic code generation is the technology that automatically generates source code or other software artefacts of a software application using tools or frameworks. Generative programming and its related term meta-programming are concepts whereby programs are written to produce software components in an automatic manner. The goal of generative programming is to improve the productivity of software developers. It is often related to code-reuse topics such as component-based software engineering. Model-driven engineering (MDE) is a software development methodology which focuses on creating domain models and using them in driving the software application development. The MDE approach aims to increase productivity by maximizing commonality between systems via reuse of standardized models.

In this PhD project, the successful candidate will explore the current state of the art on generative AI (e.g. ChatGPT), semantic models, and software development (e.g. model-driven development and software product line) and then develop a new approach to endorsing the generative AI and the semantic model to the software development so that the design and development of the software applications will be fully automated, generative, explainable, and trustworthy. The approach will provide a transformative solution to the software engineering technologies.

Applications from potential part-time students are also welcomed.

Academic qualifications

A first degree (at least a 2.2) ideally in Computer Science with a good fundamental knowledge of Software Engineering or Artificial Intelligence.

English language requirement

IELTS score must be at least 6.5 (with not less than 6.0 in each of the four components). Other, equivalent qualifications will be accepted. Full details of the University’s policy are available online.

Essential attributes:

• Experience of fundamental software design and development
• Competent in design and development of software applications
• Knowledge of generative AI and semantic models
• Good written and oral communication skills
• Strong motivation, with evidence of independent research skills relevant to the project
• Good time management

Desirable attributes:

• Some knowledge of machine learning would be beneficial

APPLICATION CHECKLIST

• Completed application form
• CV
• 2 academic references, using the Postgraduate Educational Reference Form (download)
• Research project outline of 2 pages (list of references excluded). The outline may provide details about:
  1. Background and motivation of the project. The motivation, explaining the importance of the project, should be supported also by relevant literature. You can also discuss the applications you expect for the project results.
  2. Research questions or objectives.
  3. Methodology: types of data to be used, approach to data collection, and data analysis methods.
  4. List of references.
• The outline must be created solely by the applicant. Supervisors can only offer general discussions about the project idea without providing any additional support.
• Statement no longer than 1 page describing your motivations and fit with the project.
• Evidence of proficiency in English (if appropriate)

To be considered, the application must use

• the advertised title as project title

For informal enquiries about this PhD project, please contact Prof. Xiaodong Liu - x.liu@napier.ac.uk